Module de.fabmax.physxjni
Package physx.common

Class PxCudaContextManager

java.lang.Object
physx.NativeObject
physx.common.PxCudaContextManager
public class PxCudaContextManager extends NativeObject
* Manages thread locks, and task scheduling for a CUDA context * * A PxCudaContextManager manages access to a single CUDA context, allowing it to * be shared between multiple scenes. * The context must be acquired from the manager before using any CUDA APIs unless stated differently. * * The PxCudaContextManager is based on the CUDA driver API and explicitly does not * support the CUDA runtime API (aka, CUDART).

  • Field Details

    • SIZEOF

      public static final int SIZEOF

    • ALIGNOF

      public static final int ALIGNOF
      See Also:

  • Constructor Details

    • PxCudaContextManager

      protected PxCudaContextManager()

    • PxCudaContextManager

      protected PxCudaContextManager(long address)

  • Method Details

    • wrapPointer

      public static PxCudaContextManager wrapPointer(long address)

    • arrayGet

      public static PxCudaContextManager arrayGet(long baseAddress, int index)

    • acquireContext

      public void acquireContext()
      * Acquire the CUDA context for the current thread * * Acquisitions are allowed to be recursive within a single thread. * You can acquire the context multiple times so long as you release * it the same count. * * The context must be acquired before using most CUDA functions.

    • releaseContext

      public void releaseContext()
      * Release the CUDA context from the current thread * * The CUDA context should be released as soon as practically * possible, to allow other CPU threads to work efficiently.

    • getContext

      public CUcontext getContext()
      * Return the CUcontext

    • getCudaContext

      public PxCudaContext getCudaContext()
      * Return the CudaContext

    • contextIsValid

      public boolean contextIsValid()
      * Context manager has a valid CUDA context * * This method should be called after creating a PxCudaContextManager, * especially if the manager was responsible for allocating its own * CUDA context (desc.ctx == NULL).

    • supportsArchSM10

      public boolean supportsArchSM10()
      G80

    • supportsArchSM11

      public boolean supportsArchSM11()
      G92

    • supportsArchSM12

      public boolean supportsArchSM12()
      GT200

    • supportsArchSM13

      public boolean supportsArchSM13()
      GT260

    • supportsArchSM20

      public boolean supportsArchSM20()
      GF100

    • supportsArchSM30

      public boolean supportsArchSM30()
      GK100

    • supportsArchSM35

      public boolean supportsArchSM35()
      GK110

    • supportsArchSM50

      public boolean supportsArchSM50()
      GM100

    • supportsArchSM52

      public boolean supportsArchSM52()
      GM200

    • supportsArchSM60

      public boolean supportsArchSM60()
      GP100

    • isIntegrated

      public boolean isIntegrated()
      true if GPU is an integrated (MCP) part

    • canMapHostMemory

      public boolean canMapHostMemory()
      true if GPU map host memory to GPU (0-copy)

    • getDriverVersion

      public int getDriverVersion()
      returns cached value of cuGetDriverVersion()

    • getDeviceTotalMemBytes

      public long getDeviceTotalMemBytes()
      returns cached value of device memory size

    • getMultiprocessorCount

      public int getMultiprocessorCount()
      returns cache value of SM unit count

    • getClockRate

      public int getClockRate()
      returns cached value of SM clock frequency

    • getSharedMemPerBlock

      public int getSharedMemPerBlock()
      returns total amount of shared memory available per block in bytes

    • getSharedMemPerMultiprocessor

      public int getSharedMemPerMultiprocessor()
      returns total amount of shared memory available per multiprocessor in bytes

    • getMaxThreadsPerBlock

      public int getMaxThreadsPerBlock()
      returns the maximum number of threads per block

    • getDeviceName

      public String getDeviceName()
      Returns:
      WebIDL type: DOMString [Const]

    • getDevice

      public CUdevice getDevice()
      returns device handle retrieved from driver

    • setUsingConcurrentStreams

      public void setUsingConcurrentStreams(boolean flag)
      turn on/off using concurrent streams for GPU work

    • getUsingConcurrentStreams

      public boolean getUsingConcurrentStreams()
      true if GPU work can run in concurrent streams

    • usingDedicatedGPU

      public int usingDedicatedGPU()
      * Determine if the user has configured a dedicated PhysX GPU in the NV Control Panel * Note: If using CUDA Interop, this will always return false * \returns 1 if there is a dedicated GPU * 0 if there is NOT a dedicated GPU * -1 if the routine is not implemented

    • getCuModules

      public CUmodule getCuModules()
      * Get the cuda modules that have been loaded into this context on construction * @return Pointer to the cuda modules

    • release

      public void release()
      * Release the PxCudaContextManager * * If the PxCudaContextManager created the CUDA context it was * responsible for, it also frees that context. * * Do not release the PxCudaContextManager if there are any scenes * using it. Those scenes must be released first. *